Cardiovascular Magnetic Resonance Imaging (cardiac MRI) is the gold standard for quantifying ventricular function, from which several parameters are derived. Among these, long-axis strain (LAS) is valuable for diagnosis of cardiovascular diseases. Unlike global longitudinal strain (GLS), which needs multi-plane imaging, LAS can be effectively derived from a single-plane four-chamber long-axis (4CH) cardiac MRI. Conventional analysis focuses on end-diastolic (ED) to end-systolic (ES) LAS, overlooking intermediate dynamics that could help distinguish diseases. In this study, we present a novel framework for estimating left ventricular LAS across five cardiac phases. The proposed method combines a self-supervised deformable image registration model for key frame detection with a supervised segmentation for landmark identification. LAS is calculated between ED and intermediate phases K (ED2K) and between consecutive phases (K2K). The methodology was developed and validated on the publicly available M&M2 dataset. The evaluation demonstrated significant differences between healthy individuals and patients with four of the seven cardiac diseases investigated not only in ED2ES, but also mid-systole to ES and ES to peak-flow. This emphasizes the diagnostic potential of phase-specific LAS analysis. The method is fully automated and fast, underscoring its potential for clinical application. The code and reference annotations will be made publicly available. https://github.com/Cardio-AI/cmr-las-phase2phase-analysis .